Frequency Domain Linear Prediction Research Articles

Developing children's ASR system under low-resource conditions using end-to-end architecture

The work presented in this paper aims at enhancing the performance of end-to-end (E2E) speech recognition task for children's speech under low resource conditions. For majority of the languages, there is hardly any speech data from child speakers. Furthermore, even the available children's speech corpora are limited in terms of the number of hours of data. On the other hand, large amounts of adults' speech data are freely available for research as well as commercial purposes. As a consequence, developing an effective E2E automatic speech recognition (ASR) system for children becomes a very challenging task. One may develop an ASR system using adults' speech and then use it to transcribe children's data, but this leads to very poor recognition rates due to the stark differences in the acoustic attributes of adults' and children's speech. In order to overcome these hurdles and to develop a robust children's ASR system employing E2E architecture, we have resorted to several out-of-domain and in-domain data augmentation techniques. For out-of-domain data augmentation, we have explicitly modified adults' speech to render it acoustically similar to that of children's speech before pooling into training. On the other hand, in the case of in-domain data augmentation, we have slightly modified the pitch and duration of children's speech in order to create more data capturing greater diversity. Data augmentation approaches helps in mitigating the ill-effects resulting from the scarcity of data from child domain to a certain extent. This, in turn, reduces the error rates by a large margin. In addition to data augmentation, we have also studied the efficacy of Gamma-tone frequency cepstral coefficients (GFCC) and frequency domain linear prediction (FDLP) technique along with the most commonly used Mel-frequency cepstral coefficients (MFCC) for front-end speech parameterization. Both MFCC as well as GFCC capture and model the spectral envelope of speech. On the other hand, application of linear prediction on the frequency domain representation of speech signal helps to effectively capture the temporal envelope during front-end feature extraction. Employing FDLP features that model the temporal envelope provides important cues for the perception and understanding of stop bursts and, at times, complete phonemes. This motivated us to perform a comparative experimental study of the effectiveness of the three aforementioned front-end acoustic features. In our experimental explorations, the use of proposed data augmentation in combination of FDLP features has shown a relative improvement in character error rate by 67.6% over the baseline system. The combination of data augmentation with MFCC or GFCC features is observed to result in lower recognition performances.

Data augmentation based novel approach to automatic speaker verification system

In recent times, the Automatic Speaker Verification (ASV) systems have been gaining popularity among biometric systems. Feature extraction technique, classification model, and spoof dataset are the three main components that mainly affect the performance of such systems. In recent years, researchers have proposed integrated or complex feature extraction methods at front end and combination of two or more machine learning models at backend to classify the audio samples into spoofed or bonafide. This increases the overall complexity of ASV system. Moreover, most of the spoofing datasets are highly imbalanced. Hence, to solve these issues, this paper improves front-end feature extraction by combining data augmentation approach Synthetic Minority Oversampling Technique (SMOTE) with less complex feature extraction method Frequency Domain Linear Prediction (FDLP). In the proposed system, classification of the audio samples into bonafide or spoofed samples has been done by using different backend classification models such as Random Forest (RF), K-Nearest Neighbor (KNN), Naïve Bayes (NB), Convolutional Neural Network (CNN), Long Short-Term Memory, and Bidirectional LSTM (BiLSTM). The proposed system has been built using ASVspoof PA 2019, ASVspoof LA 2019 and VSDC datasets, and has been evaluated on Logical Access (LA) attacks, Presentation attacks (PA) and multi-order replay attacks (MA). The obtained results show that combination of SMOTE oversampling with FDLP at frontend, and BiLSTM at backend outperforms all other implemented models. It provides Equal Error Rate (EER) value 0.85 %, 0.91 % and 0.55 % for PA, LA and MA attacks scenarios respectively. The performance of the proposed system has also been evaluated in the presence Gaussian noise. It can be interpreted from the obtained results that proposed FDLP-SMOTE-BiLSTM system provides better performance in noisy environment, and under different spoofing attacks scenarios.

Spectral warping and data augmentation for low resource language ASR system under mismatched conditions

The performance of an Automatic Speech Recognition System (ASR) system deteriorates while using it on children speech, due to large variations and mismatch of acoustic and linguistic variables between spoken utterances of adults and children. Another important reason for the low efficiency of ASR models is the data scarcity of children speech data for low resource-language like Punjabi. The proposed work in this paper tries to address the both challenges i.e. acoustic and linguistic variations challenge, and data scarcity problem, thereby improves performance of a children speech ASR system for Punjabi language. To handle the first issue of acoustic and linguistic variations, the proposed work uses formant modification as a spectral warping technique to reduce the variation between children speech and adult speech. Further, to address the second issue of data scarcity, this paper discusses training of ASR models on augmented children speech data. Also, the work combines well established Mel-Frequency Cepstral Coefficients (MFCC) features extraction technique with Frequency Domain Linear Prediction (FDLP) to propose MFCC-FDLP hybrid approach for front end feature extraction. For implementing the data augmentation, Tacotron 2, an end-to-end Text to Speech (TTS) generative model has been used. The proposed work uses MFCC, FDLP and hybrid MFCC + FDLP techniques for front end feature extraction, Time Delay Neural Network (TDNN) for backend acoustic modeling, and trigram language model to implement continuous Punjabi language ASR systems. To increase robustness of the proposed ASR system, we have included a batch of lexically diverse words in our pronunciation model which achieved a relative improvement of 29.44%.

Exploration of temporal dynamics of frequency domain linear prediction cepstral coefficients for dialect classification

Speakers exhibit dialectal traits in speech at sub-segmental, segmental, and supra-segmental levels. Any feature representation for dialect classification should appropriately represent these dialectal traits. Traditional segmental features such as mel-frequency cepstral coefficients (MFCCs) fail to represent sub-segmental and supra-segmental dialectal traits. This study proposes to use frequency domain linear prediction cepstral coefficients (FDLPCCs) for dialect classification inspired by its long temporal summarization during pole estimation. The i-vectors and x-vectors derived from both baseline (MFCCs, linear prediction cepstral coefficients (LPCCs), perceptual LPCCs (PLPCCs), RASTA filtered PLPCCs (PLPCC-R) and proposed (FDLPCC) features are used for identifying the dialects with support vector machine (SVM) and feed-forward neural network (FFNN) as classifiers. Proposed FDLPCC features have shown to perform better than baseline features such as MFCCs and PLPCC-Rs (best among LPCCs variants) by an absolute improvement of 3.4% and 3.9% (in unweighted average recall (UAR)), with i-vector + SVM system and 1.6% and 4.6% (in UAR), i-vector + FFNN system respectively. It is also found that there exists a complementary information between the proposed and baseline features. Furthermore current studies are compared with previous studies and it is found that performances of current studies are better than previous studies.

Dereverberation of autoregressive envelopes for far-field speech recognition

The task of speech recognition in far-field environments is adversely affected by the reverberant artifacts that elicit as the temporal smearing of the sub-band envelopes. In this paper, we develop a neural model for speech dereverberation using the long-term sub-band envelopes of speech. The sub-band envelopes are derived using frequency domain linear prediction (FDLP) which performs an autoregressive estimation of the Hilbert envelopes. The neural dereverberation model estimates the envelope gain which when applied to reverberant signals suppresses the late reflection components in the far-field signal. The dereverberated envelopes are used for feature extraction in speech recognition. Further, the sequence of steps involved in envelope dereverberation, feature extraction and acoustic modeling for ASR can be implemented as a single neural processing pipeline which allows the joint learning of the dereverberation network and the acoustic model. Several experiments are performed on the REVERB challenge dataset, CHiME-3 dataset and VOiCES dataset. In these experiments, the joint learning of envelope dereverberation and acoustic model yields significant performance improvements over the baseline ASR system based on log-mel spectrogram as well as other past approaches for dereverberation (average relative improvements of 10–24% over the baseline system). A detailed analysis on the choice of hyper-parameters and the cost function involved in envelope dereverberation is also provided.

Noise and acoustic modeling with waveform generator in text-to-speech and neutral speech conversion

This article focuses on developing a system for high-quality synthesized and converted speech by addressing three fundamental principles. Although the noise-like component in the state-of-the-art parametric vocoders (for example, STRAIGHT) is often not accurate enough, a novel analytical approach for modeling unvoiced excitations using a temporal envelope is proposed. Discrete All Pole, Frequency Domain Linear Prediction, Low Pass Filter, and True envelopes are firstly studied and applied to the noise excitation signal in our continuous vocoder. Second, we build a deep learning model based text–to–speech (TTS) which converts written text into human-like speech with a feed-forward and several sequence-to-sequence models (long short-term memory, gated recurrent unit, and hybrid model). Third, a new voice conversion system is proposed using a continuous fundamental frequency to provide accurate time-aligned voiced segments. The results have been evaluated in terms of objective measures and subjective listening tests. Experimental results showed that the proposed models achieved the highest speaker similarity and better quality compared with the other conventional methods.

Bruit-enhancing phonoangiogram filter using sub-band autoregressive linear predictive coding.

Subjective analysis of bruits has long been an element of vascular access physical exams. Digital recordings of blood flow bruits-phonoangiograms (PAGs)-may provide an objective, non-imaging measure of vascular access stenosis. We have analyzed the long-term stability in PAGs from typical dialysis patients with arteriovenous fistulas and grafts and found that typical patients have correlated PAG spectra. PAGs can be analyzed using nonlinear, sub-band frequency-domain linear prediction to produce both bruit-enhanced recordings and a bruit-enhanced power envelope. This approach is novel over prior methods because it adaptively predicts signal envelopes based on physiologic properties of blood flow determined from chronic dialysis recipients. Our results indicate that a generalized bruit-enhancing filter can be developed for dialysis vascular access. Outputs from this filter may be analyzed to determine vascular physiology, including re-stenosis risk.

Classification of vocal and non-vocal segments in audio clips using genetic algorithm based feature selection (GAFS)

The technology of music information retrieval (MIR) is an emerging field that helps in tagging each portion of an audio clip. A majority of the subtasks of MIR need an application that segments vocal and non-vocal portions. In this paper, an effort has been made to segment the vocal and non-vocal regions using some novel features based on formant structure on top of standard features. The features such as Mel-frequency cepstral coefficients (MFCCs), linear prediction cepstral coefficients (LPCCs), frequency domain linear prediction (FDLP) values, statistical values of pitch, jitter, shimmer, formant attack slope (FAS), formant heights from base-to-peak (FH1), peak-to-base (FH2), formant angle values at peak (FA1), valley (FA2), and F5 have been considered. The classifiers such as artificial neural networks (ANN), support vector machines (SVM), and random forest (RF) have been considered for a comparative study as they are powerful enough to discover huge non-linear patterns. The concept of genetic algorithms with the support of neural networks has been used to select the relevant features rather considering all dimensions, named as a genetic algorithm based feature selection (GAFS). an accuracy of 89.23% before windowing and 95.16% after windowing is obtained with the optimal feature vector of length 32 using artificial neural networks. The system developed is capable of detecting singing voice segments with an accuracy of 98%.

Speaker recognition from whispered speech: A tutorial survey and an application of time-varying linear prediction

From the available biometric technologies, automatic speaker recognition is one of the most convenient and accessible ones due to abundance of mobile devices equipped with a microphone, allowing users to be authenticated across multiple environments and devices. Speaker recognition also finds use in forensics and surveillance. Due to the acoustic mismatch induced by varied environments and devices of the same speaker, leading to increased number of identification errors, much of the research focuses on compensating for such technology-induced variations, especially using machine learning at the statistical back-end. Another much less studied but at least as detrimental source of acoustic variation, however, arises from mismatched speaking styles induced by the speaker, leading to a substantial performance drop in recognition accuracy. This is a major problem especially in forensics where perpetrators may purposefully disguise their identity by varying their speaking style. We focus on one of the most commonly used ways of disguising one’s speaker identity, namely, whispering. We approach the problem of normal-whisper acoustic mismatch compensation from the viewpoint of robust feature extraction. Since whispered speech is intelligible, yet a low-intensity signal and therefore prone to extrinsic distortions, we take advantage of robust, long-term speech analysis methods that utilize slow articulatory movements in speech production. In specific, we address the problem using a novel method, frequency-domain linear prediction with time-varying linear prediction (FDLP-TVLP), which is an extension of the 2-dimensional autoregressive (2DAR) model that allows vocal tract filter parameters to be time-varying, rather than piecewise constant as in classic short-term speech analysis. Our speaker recognition experiments on the whisper subset of the CHAINS corpus indicate that when tested in normal-whisper mismatched conditions, the proposed FDLP-TVLP features improve speaker recognition performance by 7–10% over standard MFCC features in relative terms. We further observe that the proposed FDLP-TVLP features perform better than the FDLP and 2DAR methods for whispered speech.

Speech based automatic personality perception using spectral features

Automatic personality perception is the prediction of personality that others attribute to a person in a given situation. The aim of automatic personality perception is to forecast the behaviour of the speaker perceived by the listener from nonverbal behavior. Extroversion, Conscientiousness, Agreeableness, Neuroticism, and Openness are the speaker traits used for personality assessment. In this work, a speaker trait prediction approach for automatic personality assessment is proposed. This approach is based on modeling the relationship between speech signal and personality traits using spectral features. The experiments are achieved over the SSPNet Personality Corpus. The Frequency Domain Linear Prediction and Mel Frequency Cepstral Coefficient features are extracted for the prediction of speaker traits. The classification is done using Instance based k-Nearest neighbor and Support Vector Machine (SVM) classifiers. The experimental results show that k-Nearest Neighbor classifier outperforms SVM classifier. The classification accuracy is between 90 and 100%.

A Robust Speaker Identification System Using the Responses from a Model of the Auditory Periphery.

Speaker identification under noisy conditions is one of the challenging topics in the field of speech processing applications. Motivated by the fact that the neural responses are robust against noise, this paper proposes a new speaker identification system using 2-D neurograms constructed from the responses of a physiologically-based computational model of the auditory periphery. The responses of auditory-nerve fibers for a wide range of characteristic frequency were simulated to speech signals to construct neurograms. The neurogram coefficients were trained using the well-known Gaussian mixture model-universal background model classification technique to generate an identity model for each speaker. In this study, three text-independent and one text-dependent speaker databases were employed to test the identification performance of the proposed method. Also, the robustness of the proposed method was investigated using speech signals distorted by three types of noise such as the white Gaussian, pink, and street noises with different signal-to-noise ratios. The identification results of the proposed neural-response-based method were compared to the performances of the traditional speaker identification methods using features such as the Mel-frequency cepstral coefficients, Gamma-tone frequency cepstral coefficients and frequency domain linear prediction. Although the classification accuracy achieved by the proposed method was comparable to the performance of those traditional techniques in quiet, the new feature was found to provide lower error rates of classification under noisy environments.

Significance of analytic phase of speech signals in speaker verification

The objective of this paper is to establish the importance of phase of analytic signal of speech, referred to as the analytic phase, in human perception of speaker identity, as well as in automatic speaker verification. Subjective studies are conducted using analytic phase distorted speech signals, and the adversities occurred in human speaker verification task are observed. Motivated from the perceptual studies, we propose a method for feature extraction from analytic phase of speech signals. As unambiguous computation of analytic phase is not possible due to the phase wrapping problem, feature extraction is attempted from its derivative, i.e., the instantaneous frequency (IF). The IF is computed by exploiting the properties of the Fourier transform, and this strategy is free from the phase wrapping problem. The IF is computed from narrowband components of speech signal, and discrete cosine transform is applied on deviations in IF to pack the information in smaller number of coefficients, which are referred to as IF cosine coefficients (IFCCs). The nature of information in the proposed IFCC features is studied using minimal-pair ABX (MP-ABX) tasks, and t-stochastic neighbor embedding (t-SNE) visualizations. The performance of IFCC features is evaluated on NIST 2010 SRE database and is compared with mel frequency cepstral coefficients (MFCCs) and frequency domain linear prediction (FDLP) features. All the three features, IFCC, FDLP and MFCC, provided competitive speaker verification performance with average EERs of 2.3%, 2.2% and 2.4%, respectively. The IFCC features are more robust to vocal effort mismatch, and provided relative improvements of 26% and 11% over MFCC and FDLP features, respectively, on the evaluation conditions involving vocal effort mismatch. Since magnitude and phase represent different components of the speech signal, we have attempted to fuse the evidences from them at the i-vector level of speaker verification system. It is found that the i-vector fusion is considerably better than the conventional scores fusion. The i-vector fusion of FDLP+IFCC features provided a relative improvement of 36% over the system based on FDLP features alone, while the fusion of MFCC+IFCC provided a relative improvement of 37% over the system based on MFCC alone, illustrating that the proposed IFCC features provide complementary speaker specific information to the magnitude based FDLP and MFCC features.

Local spectral variability features for speaker verification

Speaker verification techniques neglect the short-time variation in the feature space even though it contains speaker related attributes. We propose a simple method to capture and characterize this spectral variation through the eigenstructure of the sample covariance matrix. This covariance is computed using sliding window over spectral features. The newly formulated feature vectors representing local spectral variations are used with classical and state-of-the-art speaker recognition systems. Results on multiple speaker recognition evaluation corpora reveal that eigenvectors weighted with their normalized singular values are useful in representing local covariance information. We have also shown that local variability features can be extracted using mel frequency cepstral coefficients (MFCCs) as well as using three recently developed features: frequency domain linear prediction (FDLP), mean Hilbert envelope coefficients (MHECs) and power-normalized cepstral coefficients (PNCCs). Since information conveyed in the proposed feature is complementary to the standard short-term features, we apply different fusion techniques. We observe considerable relative improvements in speaker verification accuracy in combined mode on text-independent (NIST SRE) and text-dependent (RSR2015) speech corpora. We have obtained up to 12.28% relative improvement in speaker recognition accuracy on text-independent corpora. Conversely in experiments on text-dependent corpora, we have achieved up to 40% relative reduction in EER. To sum up, combining local covariance information with the traditional cepstral features holds promise as an additional speaker cue in both text-independent and text-dependent recognition.

Robust Feature Extraction Using Modulation Filtering of Autoregressive Models

Speaker and language recognition in noisy and degraded channel conditions continue to be a challenging problem mainly due to the mismatch between clean training and noisy test conditions. In the presence of noise, the most reliable portions of the signal are the high energy regions which can be used for robust feature extraction. In this paper, we propose a front end processing scheme based on autoregressive (AR) models that represent the high energy regions with good accuracy followed by a modulation filtering process. The AR model of the spectrogram is derived using two separable time and frequency AR transforms. The first AR model (temporal AR model) of the sub-band Hilbert envelopes is derived using frequency domain linear prediction (FDLP). This is followed by a spectral AR model applied on the FDLP envelopes. The output 2-D AR model represents a low-pass modulation filtered spectrogram of the speech signal. The band-pass modulation filtered spectrograms can further be derived by dividing two AR models with different model orders (cut-off frequencies). The modulation filtered spectrograms are converted to cepstral coefficients and are used for a speaker recognition task in noisy and reverberant conditions. Various speaker recognition experiments are performed with clean and noisy versions of the NIST-2010 speaker recognition evaluation (SRE) database using the state-of-the-art speaker recognition system. In these experiments, the proposed front-end analysis provides substantial improvements (relative improvements of up to 25%) compared to baseline techniques. Furthermore, we also illustrate the generalizability of the proposed methods using language identification (LID) experiments on highly degraded high-frequency (HF) radio channels and speech recognition experiments on noisy data.

Query-by-Example Spoken Term Detection using Frequency Domain Linear Prediction and Non-Segmental Dynamic Time Warping

The task of query-by-example spoken term detection (QbE-STD) is to find a spoken query within spoken audio data. Current state-of-the-art techniques assume zero prior knowledge about the language of the audio data, and thus explore dynamic time warping (DTW) based techniques for the QbE-STD task. In this paper, we use a variant of DTW based algorithm referred to as non-segmental DTW (NS-DTW), with a computational upper bound of O (mn) and analyze the performance of QbE-STD with Gaussian posteriorgrams obtained from spectral and temporal features of the speech signal. The results show that frequency domain linear prediction cepstral coefficients, which capture the temporal dynamics of the speech signal, can be used as an alternative to traditional spectral parameters such as linear prediction cepstral coefficients, perceptual linear prediction cepstral coefficients and Mel-frequency cepstral coefficients. We also introduce another variant of NS-DTW called fast NS-DTW (FNS-DTW) which uses reduced feature vectors for search. With a reduction factor of α ∈ ℕ, we show that the computational upper bound for FNS-DTW is O(mn/(α <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> )) which is faster than NS-DTW.

Temporal resolution analysis in frequency domain linear prediction

Frequency domain linear prediction (FDLP) is a technique for auto-regressive modeling of Hilbert envelopes. In this letter, the resolution properties of the FDLP model are investigated using synthetic signals with impulses immersed in noise. The effect of various factors are studied which affect the temporal resolution and this analysis suggests ways to improve the resolution of the FDLP envelopes in noisy speech. The high resolution FDLP envelopes are used to derive robust features for phoneme recognition in noisy and reverberant speech. In these experiments, the FDLP features derived from high resolution envelopes provide significant improvements.

Multistream speaker diarization of meetings recordings beyond MFCC and TDOA features

Many state-of-the-art diarization systems for meeting recordings are based on the HMM/GMM framework and the combination of spectral (MFCC) and time delay of arrivals (TDOA) features. This paper presents an extensive study on how multistream diarization can be improved beyond these two sets of features. While several other features have been proven effective for speaker diarization, little efforts have been devoted to integrate them into the MFCC + TDOA state-of-the-art baseline and to the authors’ best knowledge, no positive results have been reported so far. The first contribution of this paper consists in analyzing the reasons of this, investigating through a set of oracle experiments the robustness of the HMM/GMM diarization when also other features (the modulation spectrum features and the frequency domain linear prediction features) are integrated. The second contribution of the paper consists in introducing a non-parametric multistream diarization method based on the information bottleneck (IB) approach. In contrary to the HMM/GMM which makes use of log-likelihood combination, it combines the feature streams in a normalized space of relevance variables. The previous analysis is repeated revealing that the proposed approach is more robust and can actually benefit from other sources of information beyond the conventional MFCC and TDOA features. Experiments based on the rich transcription data (heterogeneous meetings data recorded in several different rooms) show that it achieves a very competitive error of only 6.3% when four feature streams are used, compared to the 14.9% of the HMM/GMM system. Those results are analyzed in terms of error sensitivity to the stream weightings. To the authors’ best knowledge this is the first successful attempt to reduce the speaker error combining other features with the MFCC and the TDOA and the first study to show the shortcomings of the HMM/GMM in going beyond this baseline. As last contribution, the paper also addresses issues related to the computational complexity of multistream approaches.

Temporal envelope compensation for robust phoneme recognition using modulation spectrum

A robust feature extraction technique for phoneme recognition is proposed which is based on deriving modulation frequency components from the speech signal. The modulation frequency components are computed from syllable-length segments of sub-band temporal envelopes estimated using frequency domain linear prediction. Although the baseline features provide good performance in clean conditions, the performance degrades significantly in noisy conditions. In this paper, a technique for noise compensation is proposed where an estimate of the noise envelope is subtracted from the noisy speech envelope. The noise compensation technique suppresses the effect of additive noise in speech. The robustness of the proposed features is further enhanced by the gain normalization technique. The normalized temporal envelopes are compressed with static (logarithmic) and dynamic (adaptive loops) compression and are converted into modulation frequency features. These features are used in an automatic phoneme recognition task. Experiments are performed in mismatched train/test conditions where the test data are corrupted with various environmental distortions like telephone channel noise, additive noise, and room reverberation. Experiments are also performed on large amounts of real conversational telephone speech. In these experiments, the proposed features show substantial improvements in phoneme recognition rates compared to other speech analysis techniques. Furthermore, the contribution of various processing stages for robust speech signal representation is analyzed.

Autoregressive Models of Amplitude Modulations in Audio Compression

We present a scalable medium bit-rate wide-band audio coding technique based on frequency-domain linear prediction (FDLP). FDLP is an efficient method for representing the long-term amplitude modulations of speech/audio signals using autoregressive models. For the proposed audio codec, relatively long temporal segments (1000 ms) of the input audio signal are decomposed into a set of critically sampled sub-bands using a quadrature mirror filter (QMF) bank. The technique of FDLP is applied on each sub-band to model the sub-band temporal envelopes. The residual of the linear prediction, which represents the frequency modulations in the sub-band signal, are encoded and transmitted along with the envelope parameters. These steps are reversed at the decoder to reconstruct the signal. The proposed codec utilizes a simple signal independent nonadaptive compression mechanism for a wide class of speech and audio signals. The subjective and objective quality evaluations show that the reconstruction signal quality for the proposed FDLP codec compares well with the state-of-the-art audio codecs in the 32-64 kbps range.

Computer-implemented methods and systems for modeling and recognition of speech

In accordance with the present invention, computer implemented methods and systems are provided for representing and modeling the temporal structure of audio signals. In response to receiving a signal, a time-to-frequency domain transformation on at least a portion of the received signal to generate a frequency domain representation is performed. The time-to-frequency domain transformation converts the signal from a time domain representation to the frequency domain representation. A frequency domain linear prediction (FDLP) is performed on the frequency domain representation to estimate a temporal envelope of the frequency domain representation. Based on the temporal envelope, one or more speech features are generated.